AI for Developers
Agent skill (SKILL.md) Open source MIT 10.4k

Claude-Red

About 80 offensive security skills for penetration testing, each focused on one attack surface.

Install

For this project
$ npx skills add SnailSploit/Claude-Red -a claude-code
For every project
$ npx skills add SnailSploit/Claude-Red -a claude-code -g

Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).

When to use

Use it on penetration tests and red-team engagements where you're authorized, to bring Claude up to speed on a specific attack surface quickly.

claude-red is a library of about 80 offensive security skills, each a SKILL.md file that gives Claude a methodology for one attack surface. Topics run from SQL injection to shellcode, and include Active Directory, API and JWT testing, OAuth, CI/CD pipelines and AI security. Skills load on demand from conversational triggers, so you don't pay context for the ones you aren't using.

The README lists authorized red teaming among its use cases and the skills are for security professionals. Use them only against systems you have written permission to test.

Related skills

All skills